Radiologists have different training and clinical experiences, so they may provide various segmentation annotations for a lung nodule, which causes segmentation uncertainty among multiple annotations. Conventional methods usually chose a single annotation as the learning target or tried to learn a latent space of various annotations. Still, they wasted the valuable information of consensus or disagreements ingrained in the multiple annotations. This paper proposes an Uncertainty-Aware Attention Mechanism (UAAM), which utilizes consensus or disagreements among annotations to produce a better segmentation. In UAAM, we propose a Multi-Confidence Mask (MCM), which is a combination of a Low-Confidence (LC) Mask and a High-Confidence (HC) Mask. LC mask indicates regions with low segmentation confidence, which may cause different segmentation options among radiologists. Following UAAM, we further design an Uncertainty-Guide Segmentation Network (UGS-Net), which contains three modules:Feature Extracting Module captures a general feature of a lung nodule. Uncertainty-Aware Module produce three features for the annotations' union, intersection, and annotation set. Finally, Intersection-Union Constraining Module use distances between three features to balance the predictions of final segmentation, LC mask, and HC mask. To fully demonstrate the performance of our method, we propose a Complex Nodule Challenge on LIDC-IDRI, which tests UGS-Net's segmentation performance on the lung nodules that are difficult to segment by U-Net. Experimental results demonstrate that our method can significantly improve the segmentation performance on nodules with poor segmentation by U-Net.

翻译：放射科医生因训练和临床经验不同，可能对肺结节提供多种分割标注，导致多标注间的分割不确定性。传统方法通常选择单一标注作为学习目标，或尝试学习多种标注的潜在空间，但仍浪费了多标注中蕴含的共识或分歧信息。本文提出不确定性感知注意力机制（Uncertainty-Aware Attention Mechanism, UAAM），利用标注间的共识或分歧产生更优分割结果。在UAAM中，我们提出多置信度掩码（Multi-Confidence Mask, MCM），由低置信度（Low-Confidence, LC）掩码和高置信度（High-Confidence, HC）掩码组合而成。LC掩码指示分割置信度较低的区域，这些区域可能导致放射科医生产生不同的分割选项。基于UAAM，我们进一步设计不确定性引导分割网络（Uncertainty-Guide Segmentation Network, UGS-Net），包含三个模块：特征提取模块捕获肺结节的通用特征，不确定性感知模块为标注的并集、交集和标注集生成三种特征，最后交集-并集约束模块利用三种特征间的距离平衡最终分割、LC掩码和HC掩码的预测。为充分展示方法性能，我们在LIDC-IDRI数据集上提出复杂结节挑战任务，测试UGS-Net对U-Net难以分割的肺结节的分割性能。实验结果表明，本方法能显著提升对U-Net分割效果不佳的结节的分割性能。